---
title: Marigold-V2
canonical_url: "https://www.modelscope.cn/studios/huawei-bayerlab/Marigold-V2"
md_url: "https://www.modelscope.cn/studios/huawei-bayerlab/Marigold-V2.md"
repository: huawei-bayerlab/Marigold-V2
chinese_name: "Marigold V2 在线演示：生成式计算机视觉"
last_updated: 2026-09-13
sdk_type: gradio
sdk_version: 6.17.3
downloads: 0
stars: 3
---

# Marigold-V2

> Marigold-V2 - huawei-bayerlab 在 ModelScope 创建的在线 Demo。Depth, surface normals, and albedo from a single image

huawei-bayerlab/Marigold-V2 是 ModelScope 魔搭社区上的在线可交互 Demo（创空间），基于 gradio 6.17.3 构建，中文名为「Marigold V2 在线演示：生成式计算机视觉」。

- **Repository**: huawei-bayerlab/Marigold-V2
- **SDK**: gradio
- **SDK version**: 6.17.3
- **Downloads**: 0
- **Stars**: 3
- **Last updated**: 2026-09-13

Source: https://www.modelscope.cn/studios/huawei-bayerlab/Marigold-V2

---

## Marigold V2

Depth, surface normals, and albedo from a single image. The authors' demo of
*Marigold V2: Revisiting Diffusion Transformers for Monocular Depth Estimation*
(ACM TOG, SIGGRAPH Asia 2026). Four models run on every input: depth,
see-through depth, surface normals, and albedo. Pick any two of them with the
selectors under the slider and drag to compare.

#### Clone with HTTP
```bash
 git clone https://www.modelscope.cn/studios/huawei-bayerlab/Marigold-V2.git
```

#### Citation
```bibtex
@article{pavlovic2026marigoldv2,
    author = {Pavlovic, Igor and Wandel, Thiemo and Obukhov, Anton and Bartolomei, Luca and Davydov, Andrey and Tosi, Fabio and Poggi, Matteo and S{\"u}sstrunk, Sabine and Dai, Dengxin},
    title = {Marigold V2: Revisiting Diffusion Transformers for Monocular Depth Estimation},
    year = {2026},
    issue_date = {December 2026},
    publisher = {Association for Computing Machinery},
    volume = {45},
    number = {6},
    url = {https://doi.org/10.1145/3842528},
    doi = {10.1145/3842528},
    journal = {ACM Trans. Graph.},
    month = dec,
    articleno = {204},
    numpages = {14}
}
```